AI product
Griffin is Tavus's first Human Interaction Model (HIM), a real-time, full-duplex video-to-video system for face-to-face conversation. It continuously processes incoming audio and video, models conversational state, and decides when and how to respond, including turn-taking, interruptions, backchannels, expressions, gestures, and responses to visual context and pauses.
Its architecture combines a Continuous Conversational Modeling engine with streaming speech and video generation. The conversational engine operates at regular sub-second intervals, while the audiovisual generation system converts its speech and nonverbal control signals into streaming audio and video; every frame is generated in real time from a reference image, including the surrounding scene. Griffin-Lite is described as a research preview available to a select group of early testers, with a broader release planned.
1 use taken from transcripts — each links to the moment in the video.
Tavus's first human interaction model for real-time face-to-face conversation: a unified video-to-video system that listens while speaking, reads expressions and gaze, and generates speech and video in real time from one reference image.
1 in the library.